Home - GiorgosMethe/Soft-Robots-Novelty-Search GitHub Wiki
Evolution of Soft-Robots by Novelty Search!
Problem Description
Soft robotics is a vivid research field on the science and engineering aspects of soft materials in mobile machines. Recent development in soft robotics and evolutionary optimization have shown the possibility to simultaneously evolve the morphology and locomotion of soft robots. Generative encoding coupled with neural evolution of augmented topologies (NEAT) shows promising results. It is of interest to study the development of different types of locomotion in low gravity environments while rewarding diversity at the behavioral level. Unlike most evolutionary algorithms, novelty search seeks novel behaviors and has no defined objective (e.g. distance traveled or speed). This research could result in a taxonomy of possible locomotion strategies at a given (low) gravity level that inspire new concepts for future robotic missions.
The simulator which is used is VoxCad which uses Voxelyze physics engine created by Jonathan Hiller and Hod Lipson.